© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 45665
    Prev
    Next
    INDEX
    Explanations

    the use of the preposition "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    481
    +0.15
    0.7%
    665
    +0.13
    0.6%
    591
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.15
    0.04
    665
    +0.13
    0.03
    549
    +0.12
    0.02
    Negative Logits
     teasp
    -0.78
     veto
    -0.78
     vetoed
    -0.70
     supplied
    -0.69
    aurus
    -0.68
     stopp
    -0.68
     racked
    -0.66
     topped
    -0.65
     ported
    -0.64
     conceded
    -0.64
    POSITIVE LOGITS
     Flavoring
    0.82
     seeing
    0.76
     Buddhism
    0.74
     Catholicism
    0.69
     sensation
    0.69
     neuroscience
    0.69
     discovering
    0.68
     scent
    0.68
     Taste
    0.67
     astronomy
    0.66
    Activations Density 0.087%

    No Known Activations